An adaptation of EPCA to image compression and reconstruction

Principal Component Analysis (PCA) and other SVD related approaches are commonly used in dimension reduction and reconstruction of images. However, as linear methods they may not be appropriate for some non-linear cases. Recently a new approach named as Exponential Family Principle Component Analysis (E-PCA) is proposed for non-linear compression and has been successfully used to solve the belief states' dimension reduction of Partially observable Markov Decision Process (POMDP). In this paper, we attempted to adapt E-PCA to image compression and reconstruction due to the reason that it can guarantee nonnegative reconstruction and is fit for some nonlinearly distributed data. The original E-PCA formulations are also simplified in this paper to accelerate the parameters learning process. Experiments are performed on some standard image data sets to verify the effectiveness of E-PCA on image compression. From the experimental results, we can conclude that the new adaption of E-PCA on image compression is particularly effective when the image data follows some kinds of distribution.